An exact algebraic identity plus low-rank SVD and Haar-measure null-space approximation reduce per-point mean curvature cost from O(m^4) to O(k^2 m + k m p^2) with 50-300x speedups and negligible accuracy loss.
hub
van Rijn, Bernd Bischl, and Luis Torgo
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
ScoreStop introduces a functional score test for early stopping in gradient boosting, testing the null that the current predictor minimizes population risk with a scale-invariant statistic of known asymptotic distribution.
Presents pseudo-polynomial DP algorithm O(W k n²) for weighted kNN Banzhaf valuation and O(n k²) for unweighted, plus Monte Carlo estimators, after proving #P-hardness.
PFN-TS converts PFN posterior predictives into mean-reward samples for Thompson sampling using a subsampled predictive CLT, with consistency proofs, regret bounds, and strong empirical performance on synthetic and real bandit benchmarks.
FLOWGEM generates complete data under non-monotone MAR missingness by discretizing Wasserstein gradient flows with a local linear density-ratio estimator to minimize expected KL divergence over missingness patterns.
Defines saturation index S(K) = erank(Σ̂_W^(K))/K that identifies when linear discriminant stabilizes in binary few-shot classification, with empirical phase diagram and stopping-rule AUC of 0.752 on 17 tasks.
Bayesian PCFG generates synthetic physics-like regression datasets matching eight structural features of the Feynman corpus and enabling equivalent hyperparameter tuning performance to real data.
Introduces gradient-discrepancy acquisition criterion derived from Luo et al. (2022) generalization bound for active learning.
Quantum kernel methods show no statistically significant edge over strong classical baselines on tabular classification tasks, with current feature maps failing to match the spectral properties of the best classical kernel.
TFMPathy applies tabular foundation models to summary statistics of visual features for subject-generalizable empathy detection under strong privacy constraints, with improved cross-subject performance on a public benchmark.
Derives optimal low-rank subspace for Laplace approx in BNNs, provides scalable outperforming version, and new comparison metric.
Soft Learning optimally combines heterogeneous ML specialists via cross-validated non-negative least squares, achieving top performance on 70% of 37 datasets with formal guarantees and 72-435x CPU speedups over deep networks.
The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.
TabGRAA applies group-relative advantage alignment in an iterative reward-guided post-training loop to improve tabular language model generators on fidelity, utility, and privacy trade-offs across five benchmarks.
Large-scale neutral benchmark of survival models on low-dimensional right-censored data finds Cox PH performs comparably to more complex methods across discrimination, calibration, and predictive metrics.
A CBR system based on similarity of local explanations provides visualizations that fraud analysts at a Dutch bank found useful and easy to use for processing ML-generated fraud alerts.
Human-grounded evaluation finds no significant performance improvement from adding SHAP explanations to model confidence scores in alert processing.
citing papers explorer
-
Efficient Mean Curvature Computation on High-Dimensional Data Manifolds
An exact algebraic identity plus low-rank SVD and Haar-measure null-space approximation reduce per-point mean curvature cost from O(m^4) to O(k^2 m + k m p^2) with 50-300x speedups and negligible accuracy loss.
-
ScoreStop: Gradient-based early stopping using functional score tests
ScoreStop introduces a functional score test for early stopping in gradient boosting, testing the null that the current predictor minimizes population risk with a scale-invariant statistic of known asymptotic distribution.
-
Efficient Banzhaf-Based Data Valuation for $k$-Nearest Neighbors Classification
Presents pseudo-polynomial DP algorithm O(W k n²) for weighted kNN Banzhaf valuation and O(n k²) for unweighted, plus Monte Carlo estimators, after proving #P-hardness.
-
PFN-TS: Thompson Sampling for Contextual Bandits via Prior-Data Fitted Networks
PFN-TS converts PFN posterior predictives into mean-reward samples for Thompson sampling using a subsampled predictive CLT, with consistency proofs, regret bounds, and strong empirical performance on synthetic and real bandit benchmarks.
-
Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient Flows
FLOWGEM generates complete data under non-monotone MAR missingness by discretizing Wasserstein gradient flows with a local linear density-ratio estimator to minimize expected KL divergence over missingness patterns.
-
A Spectral Phase Diagram for Binary Few-Shot Classification: Intrinsic Dimensionality, Geometric Saturation, and Representational Diagnosis
Defines saturation index S(K) = erank(Σ̂_W^(K))/K that identifies when linear discriminant stabilizes in binary few-shot classification, with empirical phase diagram and stopping-rule AUC of 0.752 on 17 tasks.
-
Synthics: Synthetic Physics-like Datasets for Machine Learning
Bayesian PCFG generates synthetic physics-like regression datasets matching eight structural features of the Feynman corpus and enabling equivalent hyperparameter tuning performance to real data.
-
Gradient-Discrepancy Acquisition for Pool-Based Active Learning
Introduces gradient-discrepancy acquisition criterion derived from Luo et al. (2022) generalization bound for active learning.
-
Benchmarking Quantum Kernel Support Vector Machines Against Classical Baselines on Tabular Data: A Rigorous Empirical Study with Hardware Validation
Quantum kernel methods show no statistically significant edge over strong classical baselines on tabular classification tasks, with current feature maps failing to match the spectral properties of the best classical kernel.
-
Privacy-Preserving Empathy Detection in Video Interactions
TFMPathy applies tabular foundation models to summary statistics of visual features for subject-generalizable empathy detection under strong privacy constraints, with improved cross-subject performance on a public benchmark.
-
Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks
Derives optimal low-rank subspace for Laplace approx in BNNs, provides scalable outperforming version, and new comparison metric.
-
Soft Learning
Soft Learning optimally combines heterogeneous ML specialists via cross-validated non-negative least squares, achieving top performance on 70% of 37 datasets with formal guarantees and 72-435x CPU speedups over deep networks.
-
Explainable AI Isn't Enough! Rethinking Algorithmic Contestability
The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.
-
Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training
TabGRAA applies group-relative advantage alignment in an iterative reward-guided post-training loop to improve tabular language model generators on fidelity, utility, and privacy trade-offs across five benchmarks.
-
A Large-Scale Neutral Comparison Study of Survival Models on Low-Dimensional Data
Large-scale neutral benchmark of survival models on low-dimensional right-censored data finds Cox PH performs comparably to more complex methods across discrimination, calibration, and predictive metrics.
-
Case-Based Reasoning for Assisting Domain Experts in Processing Fraud Alerts of Black-Box Machine Learning Models
A CBR system based on similarity of local explanations provides visualizations that fraud analysts at a Dutch bank found useful and easy to use for processing ML-generated fraud alerts.
-
A Human-Grounded Evaluation of SHAP for Alert Processing
Human-grounded evaluation finds no significant performance improvement from adding SHAP explanations to model confidence scores in alert processing.